Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 505 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8754. Min Range: -7.8754
Max Act: 7.8754. Min Act: -0.1700
Data Index: 3138821 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8754. Min Range: -7.8754
Max Act: 7.8754. Min Act: -0.1700
Data Index: 2183552 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8754. Min Range: -7.8754
Max Act: 7.6254. Min Act: -0.1700
Data Index: 2062687 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8754. Min Range: -7.8754
Max Act: 7.6254. Min Act: -0.1700
Data Index: 6737889 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8754. Min Range: -7.8754
Max Act: 7.5942. Min Act: -0.1700
Data Index: 8201644 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8754. Min Range: -7.8754
Max Act: 7.4692. Min Act: -0.1700
Data Index: 6626120 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8754. Min Range: -7.8754
Max Act: 7.4379. Min Act: -0.1700
Data Index: 7932557 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8754. Min Range: -7.8754
Max Act: 7.4379. Min Act: -0.1700
Data Index: 5033607 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8754. Min Range: -7.8754
Max Act: 7.3754. Min Act: -0.1700
Data Index: 6383306 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8754. Min Range: -7.8754
Max Act: 7.3754. Min Act: -0.1700
Data Index: 8141321 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8754. Min Range: -7.8754
Max Act: 7.3754. Min Act: -0.1700
Data Index: 1950011 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8754. Min Range: -7.8754
Max Act: 7.3129. Min Act: -0.1700
Data Index: 1759726 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8754. Min Range: -7.8754
Max Act: 7.3129. Min Act: -0.1700
Data Index: 2229039 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8754. Min Range: -7.8754
Max Act: 7.3129. Min Act: -0.1700
Data Index: 8259250 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8754. Min Range: -7.8754
Max Act: 7.2817. Min Act: -0.1700
Data Index: 2608585 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8754. Min Range: -7.8754
Max Act: 7.2504. Min Act: -0.1700
Data Index: 3800400 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8754. Min Range: -7.8754
Max Act: 7.2192. Min Act: -0.1700
Data Index: 3139617 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8754. Min Range: -7.8754
Max Act: 7.2192. Min Act: -0.1700
Data Index: 2476012 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8754. Min Range: -7.8754
Max Act: 7.2192. Min Act: -0.1700
Data Index: 4943459 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8754. Min Range: -7.8754
Max Act: 7.1567. Min Act: -0.1700
Data Index: 8051838 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19